//
you're reading...
Business, Science

Is Google (Facebook;Twitter) the World’s Best Economist?

I have been wondering for a while why Economists haven’t made better use of Google keyword search analytics as an economic tool after hearing how Google can predict flu outbreaks with surprising accuracy:

http://blogs.wsj.com/health/2010/05/17/google-flu-trends-good-at-suggesting-not-pinpointing-flu-cases/

While Google flu trends is a coarse indicator, I wondered if other Google search terms could be more accurate short-term predictors of patterns. Then I recently came across this article:

http://campaignstops.blogs.nytimes.com/2012/10/20/googles-crystal-ball/

Which got me thinking about a conversation I had with a nephew-in-law, a Cambridge-trained Economist who works for Google in London. He mentioned in August that Google examines certain search terms that are diagnostic for a country’s economic performance all the time (in order to target marketing campaigns, for example) and that their prediction algorithms were forecasting Germany’s economy going in to recession. Two weeks later a Financial Times article stated that the latest economic indicators confirmed that Germany’s economy had shrunk for the past two quarters, the official definition of a recession.

Then I heard this recent article about Facebook “likes” being accurate predictors of a company’s stock price:

http://www.npr.org/blogs/alltechconsidered/2012/10/23/163434283/how-much-is-a-like-on-facebook-worth-for-a-companys-share-price

How useful is “Sentiment Analysis” to the prediction and analysis of economic trends, theories and predictions? Some interesting academic publications suggest a rich future for this technology:

http://www.cs.cornell.edu/home/llee/opinion-mining-sentiment-analysis-survey.html

http://www.asb.unsw.edu.au/schools/economics/Documents/A.Logunov%20-%20A%20Tweet%20In%20Time%20-%20Can%20Twitter%20Sentiment%20Analysis%20Improve%20Economic%20Indicator%20Estimation.pdf

Twitter has the capacity to provide real-time sentiment analysis, a fact not lost on consumer brands that rely on customer feedback to engage customers in a variety of ways:

http://smallbiztrends.com/2010/03/tracking-twitter-sentiment.html

Academic and commercial research into Twitter also suggests how real-time aggregate feeds can lead to better predictions of economic trends:

http://arxiv.org/abs/0911.1583/

http://academic.research.microsoft.com/Paper/13273599

Is this the future of hedge-funds and options trading? Apparently a number of hedge funds think so:

http://cs229.stanford.edu/proj2011/TrusheimChakoumakosYendluri-Automated_Market_Sentiment_analysis_of_Twitter_for_Options_Trading.pdf

Advertisements

Discussion

No comments yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

w

Connecting to %s

%d bloggers like this: